Oh please tell me, where can i buy the magic glass globe, that told you that.

[edit] BTW: If you're such a wizard with the glass globe:
Can you tell, why the traffic on the link is actually lower than before the outage?

No glass globe required in his case, just a little reading.
See Technical News, "... our upload/download server, which has been buckling under the load since the outage earlier this week. This server is completely CPU bound,..."
Since evrything requires some CPU cycles, including network requests, the network traffic is simply being capped by the lack of CPU cycles.

---

No glass globe required in his case, just a little reading.
See Technical News, "... our upload/download server, which has been buckling under the load since the outage earlier this week. This server is completely CPU bound,..."
Since evrything requires some CPU cycles, including network requests, the network traffic is simply being capped by the lack of CPU cycles.

That still doesn't explain the lower traffic or did they change hardware to slower machines? If there is suddenly more cpu power demand, then from what? Some untested unoptimized alpha level server code? It should be investigated instead of hoping to throw more hardware at this issue at a later time.

---

Aloha, Uli

Oh please tell me, where can i buy the magic glass globe, that told you that.

[edit] BTW: If you're such a wizard with the glass globe:
Can you tell, why the traffic on the link is actually lower than before the outage?

No glass globe required in his case, just a little reading.
See Technical News, "... our upload/download server, which has been buckling under the load since the outage earlier this week. This server is completely CPU bound,..."
Since evrything requires some CPU cycles, including network requests, the network traffic is simply being capped by the lack of CPU cycles.

Well, that's a good theory, but the daily graph (click on the first hourly graph) shows that there was a great increase in network traffic right after the outage, rising to ~95Mbps, then settling down (July 13-14, about the time the Technical News message you cited was posted) to ~50Mbps. So where was the cap on Tuesday? And why is the traffic ~10Mbps lower than it was before the outage? I think that you don't know the answers, that you are just guessing; and the devs haven't updated their information in two days.

At this time yesterday I had 261 waiting to upload. Today I have 267 waiting. During the planned outage I got up to nearly 400, so there was some progress, but that seems to have stopped.

You have your computers hidden. I wanted to see what you were running that you are getting numbers like that.

by modif of one file, it's for increase the rank ;)

---

http://www.boincstats.com/stats/banner.php?id=10628

From the front page:

July 15, 2005
The data server is continuing to drop connections, which is very unusual this long after an outage. We are working to figure out why.

So mister "i know all", who was right? ;)

---

Aloha, Uli

Hi,
I am up to 19 waiting to be uploaded at this time, 4 days after the crash. Yet the other projects are working fine.

Any more news from the uni on the time frame to get back to normal?

---

A simple country boy waiting for...
A sign of any kind.

From the front page:

July 15, 2005
The data server is continuing to drop connections, which is very unusual this long after an outage. We are working to figure out why.

So mister "i know all", who was right? ;)

A lesson to all the "Cheerleaders" - common sense really. If you haven't been TOLD there is a problem, that doesn't mean there isn't one. Next time you feel like belittling a comment think on: you, like any BOINC user, are basing your opinions on what you are told, not what is fact.

So be somewhat gentler with folks........

---

From the front page:

July 15, 2005
The data server is continuing to drop connections, which is very unusual this long after an outage. We are working to figure out why.

So mister "i know all", who was right? ;)

A lesson to all the "Cheerleaders" - common sense really. If you haven't been TOLD there is a problem, that doesn't mean there isn't one. Next time you feel like belittling a comment think on: you, like any BOINC user, are basing your opinions on what you are told, not what is fact.

So be somewhat gentler with folks........

hear hear! commonsense should prevail. But when these things start to happen, we all get worried. Hell, I thought my internet connection was going faulty, but now i know the problems are at Berkeley - phew!

---

At this time yesterday I had 261 waiting to upload. Today I have 267 waiting. During the planned outage I got up to nearly 400, so there was some progress, but that seems to have stopped.

You have your computers hidden. I wanted to see what you were running that you are getting numbers like that.

Mostly 866 MHz and 933 MHz P3's actually, with a few P4's in the mix. It's the L2 cache that makes the difference. I have some 933 MHz P3's with 2Mb L2 that walk all over 3.2 GHz P4's with 512K and 1Mb L2. The other thing is that I have a couple dozen of them, that really helps.

---

Mostly 866 MHz and 933 MHz P3's actually, with a few P4's in the mix. It's the L2 cache that makes the difference. I have some 933 MHz P3's with 2Mb L2 that walk all over 3.2 GHz P4's with 512K and 1Mb L2. The other thing is that I have a couple dozen of them, that really helps.

With 2 million SETI cobblestones I'd guess you have more than a "couple dozen..." ;)

---

Mostly 866 MHz and 933 MHz P3's actually, with a few P4's in the mix. It's the L2 cache that makes the difference. I have some 933 MHz P3's with 2Mb L2 that walk all over 3.2 GHz P4's with 512K and 1Mb L2. The other thing is that I have a couple dozen of them, that really helps.

With 2 million SETI cobblestones I'd guess you have more than a "couple dozen..." ;)

and you are just shy of the million mark yourself

---

To day they have try to solve this problem for 4 days an still no success.
What kind of university is this? ;)

What problem? There is no problem to be fixed.
OTH, If you are talking about the lack of capacity to handle the workload, then it is simply a matter of budgets - it's a university like every other in the world, without infinite money available.

The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill.

And how would you know, are you an expert on the INTERNET, systems and the University or are you blowing wind....

---

Semper Eadem
So long Paul, it has been a hell of a ride.

Park your ego's, fire up the computers, Science YES, Credits No.

I keep expecting Rod Serling to pop up at some point and say "And here's azwoody.. who think that there are general problems with seti/boinc, but yet has has no problem with uploads or downloads for the last 2 days. Welcome to the Twlight Zone.."

Things have been working fine for me for the last 2 days when it comes to uploads/downloads. I have seen results getting defered a total of two times, and both went through on the next attempt Granted, I didn't have a backlog before the outage, and now am only doing seti at 50% on one system. But from what I see, it's working ok.

---

The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill.

And how would you know, are you an expert on the INTERNET, systems and the University or are you blowing wind....

Well, Blank, are you? This guy brought up a problem, and points out that they have had 100 hours to work on it. This seems to be the best place to raise these concerns because the devs read here (and they have recently pointed out that there does seem to be a problem). Too many people here simply dismiss posts about problems like the one Tomas pointed out, as mere complaints, or to use your term "blowing wind". Why does it concern you that someone is letting Berkeley know about a problem?

The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill.

And how would you know, are you an expert on the INTERNET, systems and the University or are you blowing wind....

Well, Blank, are you? This guy brought up a problem, and points out that they have had 100 hours to work on it. This seems to be the best place to raise these concerns because the devs read here (and they have recently pointed out that there does seem to be a problem). Too many people here simply dismiss posts about problems like the one Tomas pointed out, as mere complaints, or to use your term "blowing wind". Why does it concern you that someone is letting Berkeley know about a problem?

It's simple Tom.. There are some that refuse to acknowledge that UCB would miss something, misunderstand something, or miss keeping volenteirs in the loop. The "cheerleaders" have been here since day one, and IMHO, are NOT doing the project a service. Just look at some of the responses to people just moving over from classic, or found they couldn't join classic and were directed here, with zero experience with seti!

I wonder how "Blank" knows that they spent 100 hours (is that staff time or real time?) working on it? My guess is that it's been back up 100 hours (realtime) and Blank assumes that they've been addressing this specific problem since then.. But in reality, might have only known there's a problem for a few hours (realtime) when someone posted it here. Before that, they thought it was just the "normal" downtime delay. just his opionion on my part.

In answer to "are you an expert on the INTERNET, systems and the University", I can say yes to the first two Been working/programming on the net since it's whole map would fit on a 4'x3' sheet and hung on the wall, on about any system you can imagine.... For number 3, all I can say is I've seen how the seti group works for 13 days short of 6 years. I think that qualifies as at least "some experience" in how the seti group at UCB works!! (at least as seen by it's thousands of volinteers!)

---

Wow!!! How great thou art!!

The project is open source so that users such as you and me can make suggestions or improvements. Wish you experts would download the source code look through it and make the corrections. If you know all the answers why withhold the information? Why don’t you get to work on the problems?

Only thing I can think of is that you would rather bitch about the problems rather than become part of the solution.

---

Boinc....Boinc....Boinc....Boinc....

Hello azwoody,

It's been a long time since we've crossed paths, as I spend most of my time (when things are working right) over in the Cafe SETI. I'm glad to see you still here, pointing out problems and keeping the Berkeley folks on their toes. As I've been trying to point out to idiots like Geek@play, there is value in posting over here: just letting people know that there is a problem; it may not be their end; that others are having the same problem; and maybe the developers will work on it soon. It may look like you and I are bitching, but that is part of the process of problem solving--the first step--identifying that there is something wrong. Since I'm mostly at the Cafe when the project is going well, and you're mostly over here, I hope I don't have to come back and see you too often. Keep it up over here.

The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill.

And how would you know, are you an expert on the INTERNET, systems and the University or are you blowing wind....

Well, Blank, are you? This guy brought up a problem, and points out that they have had 100 hours to work on it. This seems to be the best place to raise these concerns because the devs read here (and they have recently pointed out that there does seem to be a problem). Too many people here simply dismiss posts about problems like the one Tomas pointed out, as mere complaints, or to use your term "blowing wind". Why does it concern you that someone is letting Berkeley know about a problem?

There is nothing wrong with bring up your comcerns, I have a big problem with the personal attacks that are included.....And I feel that of all people you know presentation is everything......

"The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill".


AZwoody go away, I have never seen you help one person, all you can do is brag and bitch......

---

Semper Eadem
So long Paul, it has been a hell of a ride.

Park your ego's, fire up the computers, Science YES, Credits No.

Now this is beyond weird. I had 26 WU's ready to upload and the list was getting longer. So I hit retry on each one followed by Abort Transfer and lo and behold, they went through!

What would cause such goofy behavior?
Try it yourselves, see if it works for you too.

---

Proud member of Team Starfire World BOINC

There is nothing wrong with bring up your comcerns, I have a big problem with the personal attacks that are included.....And I feel that of all people you know presentation is everything......

"The problem that you can't down or upload an they have worked on this problem for 100 hour. I certainly expect more form a university. It's not a matter of budget it's a lack of skill".

AZwoody go away, I have never seen you help one person, all you can do is brag and bitch......

Blank Reg, maybe Tomas doesn't express himself as well as you in English, but I didn't see his post as a personal attack. You, on the other hand, then go ahead with a personal attack on azwoody . . . you wouldn't be related to Pascal, would you?